Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Quantitative Biology Quantitative Methods

q-bio.QM Watch Quantitative Methods

Wednesday 23 September

Quantitative Methods

Prediction bias in biological ageing markers

Yiqun Lin, Ariel Yuhan Ong, Matthew Yu Heng Wong et al. (+52 more)

Biological ageing markers have attracted growing interest, with models estimating age from organ imaging or blood biomarkers. An estimated age above chronological age or the age-specific population expectation is assumed to reflect accelerated ageing and poorer health. Previous research has supported this assumption through positive associations between disease and age gaps or acceleration. However, in this study, we identified a widespread health-dependent prediction bias in ageing markers that affects their key interpretation and application. Specifically, we investigated five ageing markers derived from retinal images, brain MRI, chest radiographs, abdominal CT, and blood tests, and evaluated them using association analyses. We observed the well-recognised phenomenon of regression to the mean (RTM) in the four organ-image based markers, whereby estimated ages were shifted towards the mean age of the training cohort. More importantly, we revealed that the strength of RTM varied with health status, with stronger RTM in unhealthy than in healthy individuals. This differential RTM introduced a health-dependent prediction bias that persisted after calibration and systematically altered associations across age subgroups, suggesting that whole cohort associations may not reflect those observed within individual age subgroups. Additionally, we showed that the tested ageing markers, including PhenoAge derived from blood biomarkers, had limited ability to distinguish health status at the individual level. These findings call for careful interpretation of biological ageing markers and their use in clinical studies, and highlight the need for further development and validation before these ageing markers can reliably inform individual health assessments.
Read the full abstract

All authors Yiqun Lin, Ariel Yuhan Ong, Matthew Yu Heng Wong, Yilan Wu, Wenyi Hu, Shubhank Shobhit Verma, Broder Poschkamp, Lie Ju, Akshay Narayan, Sophie A. Martin, Maitrei Kohli, Fares Antaki, Alexander C. Heatley, Josef Huemer, Meng Wang, Ke Zou, Zheyuan Wang, Eden Ruffell, Dominic Williamson, Justin Engelmann, Hyunmin Kim, Takahiro Ninomiya, Rahul A. Jonas, Yansong Liu, Zijie Cheng, Hanyuan Zhang, Hejie Cui, Jiayang Xu, Hualiang Wang, Zuozhu Liu, Bin Pu, Chubo Liu, Kenli Li, Xinpeng Ding, Guokai Zhang, Weiru Wang, Jiaxiang Wang, Huazhu Fu, Zongyuan Ge, Xujia Liu, Mohammad Eslami, Milen Raytchev, Tobias Elze, Michael G. Morley, Neil P. Oxtoby, Daniel C. Alexander, Anthony P. Khawaja, Ching-Yu Cheng, Lisa Zhuoting Zhu, Yih Chung Tham, James H. Cole, Carol Y. Cheung, Pearse A. Keane, Siegfried K. Wagner, Yukun Zhou

Quantitative Methods · Cross-listed from cs.LG

SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference

Shiting Ruan, Xitong Ling, Qiming He et al. (+6 more)

Spatial transcriptomics (ST) profiles gene expression within tissue architecture, but its cost and experimental complexity limit routine use. Predicting spatial expression from routinely available hematoxylin and eosin (HE) images therefore offers a scalable alternative. However, conventional methods often fit high-dimensional gene outputs as independent targets, overlooking the biological coordination among genes while remaining vulnerable to high-dimensional noise and overfitting. Existing attempts to address this limitation often rely on computationally heavy graph networks or complex auxiliary supervision. We therefore introduce SpaFactor, a lightweight and efficient low-rank morphology-program-gene factorization framework. At the input, SpaFactor efficiently fuses the visual representation of the central spot with multiscale local and regional neighborhood context, yielding a histologic representation that captures cellular morphology and microenvironmental heterogeneity. For modeling, a residual MLP stably learns a nonlinear mapping from the tissue microenvironment to low-dimensional latent gene programs. These activities are decoded through shared gene loadings into coordinated multi-gene expression predictions. Across five public cohorts, SpaFactor achieves the best aggregate performance, with particularly clear improvements for spatially variable genes, and more faithfully recovers biologically organized spatial patterns. These results demonstrate that lightweight joint modeling of tissue context and gene programs can improve both predictive accuracy and biological fidelity.
Read the full abstract

All authors Shiting Ruan, Xitong Ling, Qiming He, Ziyou Yan, Huaitian Yuan, Tian Guan, Ying Xiao, Xu Guan, Yonghong He

Quantitative Methods

Circadian Derived Features for Early Discrimination Across Insomnia Severity Levels: At Least 8 Weeks of Monitoring Are Needed for Clinically Meaningful Assessment

Soheil Saghafi, Thomas C. Neylan, Qiao Li et al. (+2 more)

Background: Wearable devices provide continuous, objective measures of daily activity and offer promise for assessing sleep disorders. However, the minimum monitoring duration needed to differentiate insomnia severity remains unclear. We investigated when wearable-derived behavioral features become informative for distinguishing Insomnia Severity Index (ISI) categories and examined the contribution of Activity Count (AC) and circadian-derived features. Methods: We analyzed wearable data from 2,305 participants in the Advancing Understanding of Recovery after Trauma (AURORA) study. Separate binary classifiers were developed for four ISI categories across six follow-up periods using AC and circadian-derived feature sets. Performance was evaluated using accuracy, F1-score, precision, recall, and AUROC. Results: Classification improved with longer monitoring. Across ISI categories, approximately eight weeks was the earliest time point at which wearable-derived features consistently achieved informative discrimination, with modest improvements thereafter. Participants without clinically significant insomnia were easiest to identify, reaching an AUROC of 0.693. Circadian-derived features performed comparably to, and in several cases better than, AC features, suggesting that the temporal organization of daily activity provides information beyond overall activity volume. Conclusions: Approximately eight weeks of longitudinal wearable monitoring may represent a practical minimum for differentiating ISI-defined insomnia categories. Longer monitoring provided only incremental improvements. Circadian behavioral features show promise as digital biomarkers for objective insomnia assessment.
Read the full abstract

All authors Soheil Saghafi, Thomas C. Neylan, Qiao Li, Samuel A. McLean, Gari D. Clifford

Quantitative Methods · Cross-listed from stat.CO

Penguin data reanalyzed via Computational Taxonomy

Thomas B. Michelon, Avidane C. Caballero and Hsieh Fushing

We employ Computational Taxonomy (CT) to reanalyze the penguin data set penguins_lter by validating and addressing two biological issues: Sexual Size Dimorphism (SSD) and mate-selection criteria. Via Scientific Data Analysis (SDA) computing, CT constructs a Taxonomic Hierarchy by splitting Species first and then Sex, without involving Island, to achieve less complexity. This Taxonomic Hierarchy validates SSD as a branch comparison: (Species, Sex = Male)-vs-(Species, Sex = Female), upon which SDA explores all potential pieces of associative information from all covariate feature-sets, including interacting effects from order-2 to order-4, and then confirms them via their idiosyncratic reliability checks. The collective of confirmed information pieces are displayed on a heatmap platform to manifest underlying dynamics of SSD with explicit block-structured heterogeneity found within males and females. SSD dynamics is explained through mechanistic dependence pertaining to one chief factor consisting of up to 8 feature-sets: Body-Mass coupled by combinations of {Culmen-length,Culmen-depth, Flipper-length}, and two minor factors consisting of low-order combinations of {Culmen-length,Culmen-depth, Flipper-length}. Such Intra-Sex heterogeneity invalidates all Logistic regression modeling on SSD in the original paper. Further, we explore potential mate-selection criteria through the data-frame of Nest-ID within-species homogeneity.
Read the full abstract

Quantitative Methods

Topological Inference for Organoids

Haochen Yang, Byung Ho Lee, Anne Grapin-Botton et al. (+2 more)

The reproducibility of organ morphology and the extent to which computational models can predict morphogenesis remain difficult to quantify, particularly for organs with complex networks of fluid-filled lumina. Here, we combine Topological Data Analysis (TDA), biophysical simulation, and Bayesian inference to study lumen morphogenesis in pancreatic organoids. Lumen formation is governed by physical processes that are challenging to measure directly, including cell proliferation and luminal osmotic pressure. We simulate organoid development using a phase-field model and address the inverse problem of inferring these parameters from either time-lapse images or single morphological snapshots. Since lumen architectures vary substantially in size, structure, and connectivity, conventional geometric descriptors provide only a partial representation of their morphology. We therefore represent each organoid using SampEuler, a topological descriptor derived from the Euler Characteristic Transform (ECT). We first show that SampEuler captures morphological information encoded by established morphometrics. We then perform parameter inference using an approximate Bayesian computation (ABC) rejection framework with the SampEuler Wasserstein distance. Using synthetic organoids with known ground-truth parameters, our approach accurately recovers the osmotic pressure and the proliferation rate while revealing a compensatory trade-off between the two processes. Applied to experimental data from ten pancreatic organoids, the inferred posterior distributions are consistent with biological expectations. Together, these results establish a non-destructive, image-based pipeline for estimating otherwise inaccessible physical parameters governing lumen formation and highlight the potential of topological representations for linking complex biological morphology to mechanistic models.
Read the full abstract

All authors Haochen Yang, Byung Ho Lee, Anne Grapin-Botton, Heather A. Harrington, Helen M. Byrne

Quantitative Methods · Cross-listed from cs.LG

Pheno-GS: Phenoscape-scale Geodesic Sinkhorn

Alistair Wilkinson, Christopher J. Tape and Smita Krishnaswamy

High-throughput single-cell data is now collected across large patient cohorts. Understanding patient-level heterogeneity from cellular-level data motivates phenoscaping: embedding each single-cell distribution as a "datapoint," with distances given by optimal transport (OT). Computing geometry-aware OT at this scale, between all pairs of patient datasets, remains an open challenge, since existing methods either rely on Euclidean ground metrics that distort manifold structure or fail under sparse, unevenly sampled, or large-scale data. We present Pheno-GS (Phenoscape-scale Geodesic Sinkhorn), which computes accurate, scalable geodesic transport distances under noisy, unbalanced, large-scale settings via three components: ($1$) graph connectivity regularization for well-defined geodesics on sparse/disconnected manifolds; ($2$) an unbalanced OT formulation via KL marginal penalties; and ($3$) a batched matrix algorithm computing all pairwise distances in one heat diffusion (over $200 \times$ faster than Geodesic Sinkhorn for $500$ distributions). We validate Pheno-GS on synthetic benchmarks and a CyTOF perturbation dataset.
Read the full abstract

Quantitative Methods · Cross-listed from cs.LG

Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

Mengran Li, Bo Li, Chengyang Zhang et al. (+3 more)

AI virtual cells aim to predict cellular responses to specified interventions, yet held-out predictive performance alone does not establish use of the supplied perturbation information. This prediction-claim gap matters in agentic model discovery, where language-model agents generate and revise predictors using score-based feedback. We introduce CELLAUDIT, which audits input-use claims by asking whether an input can enter the cited computation, whether fitted predictions depend on it, and whether that dependence improves prediction of observed response. On a paired morphology-transcriptomics perturbation benchmark (BBBC047), an agent-selected predictor attains a mean held-out Global Pearson correlation coefficient (PCC) of 0.3153 but remains invariant to compound replacement; a control-profile-only predictor reaches 0.3142. Source inspection identifies a compound-query pathway blocked by singleton key-value attention, and the invariance persists after refitting with disjoint control wells. In a stratified audit of 48 candidates across two linked tasks, 47 change predictions under compound replacement on both held-out folds, but only 20 show target-loss gains with intervals above zero on both folds. On BBBC047, falsification-guided revisions recover positive mean compound contributions while retaining gains over the control-profile-only baseline. In matched sci-Plex searches, audit-enriched feedback yields higher held-out performance and larger mean compound and dose contributions across five trajectories, although paired intervals span zero. Refitting fixed designs on an independently acquired cohort shows predictive generalization need not imply generalization of input-use claims: dose contribution persists, whereas support for compound identity does not. CELLAUDIT adds a falsification layer to agentic model discovery, moving from generate-score-revise toward discover-falsify-revise.
Read the full abstract

All authors Mengran Li, Bo Li, Chengyang Zhang, Yang Yan, Jinfeng Xu, Zhenchao Tang

Quantitative Methods

BreCol: Benchmarking Classical and Deep-Learning Methods for Microbiome-Based Cancer Detection

Jeffrey M. Dick

DNA sequencing of the gut microbial community shows promise for cancer detection, but questions remain about the generalizability of results across studies. We propose BreCol, a benchmark of 2,040 16S rRNA gene sequencing runs across 26 studies spanning breast cancer, colorectal cancer, and healthy cohorts. Train-test splits are made within pre-2023 studies, while holdout evaluation uses studies from 2023 onward, reflecting temporal separation from training data. Classical models reach test/holdout AUCs of 0.77/0.60 for cancer diagnosis and 1.00/0.83 for cancer type prediction. We train the models on both cancer types simultaneously and find that colorectal cancer is often easier to detect than breast cancer. We also evaluate two deep learning models: HyenaDNA, a long-range sequence model that pools hidden states for classification, and SetBERT, a transformer that produces contextualized embeddings over sets of reads. Both deep learning models underperform the best classical methods on holdout data, though tuning training set size and the classification head yields modest gains. Our classical pipeline uses unsupervised clustering to derive features from tetramer frequencies, preserving within-run compositional signal and achieving near state-of-the-art performance without relying on taxonomic assignments. BreCol data and associated code are publicly available.
Read the full abstract

Tuesday 22 September

Quantitative Methods · Cross-listed from cs.CV

RootQuantV2: Adapting a Vision Foundation Model for Root-Trait Regression from Minirhizotron Imagery

Kinjalk Parth, Sebastian Varela and Andrew D. B. Leakey

A lack of high-throughput phenotyping solutions for root traits in field-grown crops has severely constrained understanding and improvement of below-ground traits and processes. Minirhizotrons are the standard non-destructive root-phenotyping method in field environments. Computer vision solutions are needed to allow automated trait estimation at scale, but training data is scarce and human annotations are often inaccessible because they reside in proprietary software that only exports per-image scalar totals of root length and surface area. Nevertheless, large numeric archives of these root traits already exist. RootQuant showed that the traits can be predicted directly from the whole image by regression, thus removing manually traced masks from the pipeline; RootQuantV2 takes that idea further by replacing RootQuant's CNN backbone with a self-supervised ViT. We adapt a frozen DINOv3 ViT-L/16 with a hybrid parameter-efficient scheme. Training only 11.9M parameters (3.78% of the model), RootQuantV2 achieves length and area $R^2$ of 0.950 and 0.930, respectively, while lowering length/area RMSE by 24.3%/20.7% over RootQuant. RootQuantV2 thus repurposes legacy numeric archives for high-throughput, automated root trait estimation.
Read the full abstract

Monday 21 September

Quantitative Methods · Cross-listed from q-bio.NC

Physics-constrained inference of somatic dynamics from dendritic recordings with sparse somatic supervision in weakly coupled two-compartment neuron model

Abdeltif Oujbara, Benjamin Ambrosio and M.A. Aziz-Alaoui

Somatic membrane potential is the primary determinant of neuronal output, yet it remains inaccessible in many experimental setups where only dendritic recordings are available. Reconstructing somatic dynamics from distal measurements is a challenging inverse problem, particularly when the soma and dendrites are weakly coupled, as dendritic signals represent a filtered and attenuated version of somatic activity. To address this, we use a physics-informed neural network (PINN) constrained by a two-compartment Hodgkin–Huxley model. The network is trained on dense dendritic voltage recordings and the known injected current, complemented by a small number of somatic voltage samples (at most 5% of the time points), and it reconstructs the full somatic trajectory while adjusting a selected set of somatic maximal conductances. On synthetic data from four stimulation protocols, we quantify how the reconstruction depends on the amount of somatic supervision. Without somatic samples, the present formulation returns a smooth trajectory in which the action potentials are absent and the subthreshold level is biased, with a root-mean-square error of 10–14~mV; 1% of the somatic time points is enough to recover every spike; and 5% brings the root-mean-square error to about 2~mV, spikes included, with relative errors below 0.1% on the sodium and delayed-rectifier conductances. We also compare the PINN with an unscented Kalman filter constrained by the same model and assimilating the same observations, and we assess robustness to measurement noise and to random initialization. The reconstructions reported here therefore rely on sparse somatic anchoring in addition to the dendritic recordings. The results delimit what can be inferred in this synthetic, weakly supervised two-compartment setting and identify the amount of somatic information required by the present formulation.
Read the full abstract

Quantitative Methods

Uncertainty Quantification-Incorporated Ensemble Model for Personalized Prediction of Severe Radiotherapy-Induced Immunosuppression Among Esophageal Cancer Patients

Baode Gao, Yan Chu, Zongsheng Hu et al. (+10 more)

Severe radiation-induced lymphopenia (RIL), specifically Grade 4 RIL (G4RIL), is a frequent immune toxicity and a strong predictor of poor survival for esophageal cancer patients undergoing concurrent chemoradiation therapy. This study developed an uncertainty-incorporated ensemble machine learning model to predict Absolute Lymphocyte Count (ALC) nadir using baseline clinical and dosimetric variables, supporting treatment decisions such as proton therapy selection and dose distribution optimization. A cohort of 1,491 esophageal cancer patients treated with photon or proton therapy between July 2001 and April 2022 was analyzed. A weighted ensemble model was constructed using clinical features and dosimetric variables, including the composite dosimetric score (CDS) derived from radiation dose distributions. To quantify individual-level predictive uncertainty, Cross-Residual Conformal Prediction (CRCP) was developed and evaluated against standard conformal prediction methods. Proton therapy patients maintained a significantly higher mean ALC nadir than photon patients (0.33 vs. 0.25 K/uL). The ensemble model achieved a mean absolute error of 0.0926 K/uL for ALC nadir prediction and an ROC-AUC of 0.78 for G4RIL classification. Baseline ALC, Planning Target Volume, and CDS were the most influential predictors. CRCP achieved competitive prediction interval widths with mathematically guaranteed coverage, offering a favorable balance between interval width and coverage accuracy. This framework enables risk-aware, personalized clinical decision-making in radiation oncology.
Read the full abstract

All authors Baode Gao, Yan Chu, Zongsheng Hu, Madison E. Grayson, Peter S.N. van Rossum, Clemens Grassberger, Heiko Enderling, Harald Paganetti, Ibrahim Chamseddine, Steven H. Lin, Brian P. Hobbs, Radhe Mohan, Yiqing Chen

Quantitative Methods · Cross-listed from quant-ph

Experimental evidence of generalization in quantum machine learning in small-data regime

Leena Anthony, Artemiy Burov, Nicolas Piro et al. (+2 more)

Quantum machine learning is a promising paradigm for learning from limited data, a central bottleneck in domains such as medical imaging, clinical trials, and rare diseases. Quantum convolutional neural networks (QCNNs) are particularly attractive in this setting, combining a hierarchical architecture with strong inductive bias and a parameter count that grows only logarithmically with system size. Their appeal rests on the generalization bounds of Caro et al. (2022), which show that the generalization error of a quantum model scales with the number of trainable parameters rather than with the Hilbert-space dimension, placing QCNNs in a potentially sample-efficient regime. We develop a hardware-compatible QCNN with mid-circuit measurement and classical feed-forward, and show on a binary handwritten-digit task that strong test performance is achievable from as few as 10 training samples, with the generalization error decreasing as the training set grows. At a matched 45-parameter budget the QCNN learns where an equally small classical convolutional network stays at chance, although an unconstrained classical baseline with roughly 25,000 parameters remains strongest when data are plentiful. Transpiling amplitude and angle encoded circuits across image resolutions from 2x2 to 512x512 pixels then exposes the dominant scaling bottleneck: amplitude encoding stays qubit-efficient but grows extremely deep, whereas angle encoding stays shallow but becomes qubit-prohibitive. On the medically motivated BreastMNIST benchmark the QCNN does not surpass the unconstrained classical network, yet it learns consistently above chance using orders of magnitude fewer parameters. Our results indicate that for QCNNs, learning from few samples is attainable in practice, whereas scaling to realistic image data is constrained less by optimization than by data encoding and hardware execution.
Read the full abstract

All authors Leena Anthony, Artemiy Burov, Nicolas Piro, Matteo Dal Peraro, Clément Javerzac

Quantitative Methods · Cross-listed from cs.CL

QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation

Demian Pavlyshenko and Bohdan Pavlyshenko

Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.
Read the full abstract

Quantitative Methods · Cross-listed from q-bio.BM

Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening

Kairi Furui and Masahito Ohue

Virtual screening aims to prioritize active compounds from large chemical libraries within a limited experimental budget. When applying Boltz-2 to virtual screening, a key challenge is how to use limited experimental data from the target assay to improve the prioritization of active compounds. We investigated whether fine-tuning the Boltz-2 affinity heads with a small number of binary activity labels could improve early enrichment of active compounds in hit discovery. We compared fine-tuning with 40-300 labels in a retrospective evaluation on eight MF-PCBA targets. With 300 activity measurements, fine-tuning increased the number of actives in the top 1% by a geometric mean of 1.77-fold across the eight targets and improved average precision (AP) by 2.14-fold relative to the control without fine-tuning. We also investigated whether rescoring a subset of candidates could retain the improvement in hit recovery by reranking only the top-ranked Boltz-2 candidates with the fine-tuned head. Restricting rescoring to approximately 10% of the evaluation set retained hit recovery comparable to full rescoring. These findings show that affinity-head fine-tuning with limited activity labels improves early enrichment with Boltz-2 and that this benefit can be retained when rescoring a restricted set of candidates.
Read the full abstract

Quantitative Methods · Cross-listed from cs.CV

Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea

Reza Saputra, Diah Harnoni Apriyanti, André Schuiteman et al. (+4 more)

New Guinea is the world's richest island flora (~2,856 orchid species), yet most species are represented by only a handful of photographs, far fewer than direct species-level classification requires. Methods for fine-grained identification in such species-rich, data-poor floras are needed, and it remains unclear which backbone architecture and pretraining strategy best support them. We built a two-stage system that first predicts the genus of a query photograph, then retrieves visually similar reference images of candidate species using FAISS. We compared four pretrained backbones – two Vision Transformers (ViTs; DINOv2, BioCLIP 2) and two CNNs (ConvNeXt V2-L, EfficientNetV2-L) – fine-tuned under an identical protocol on a fixed, species-stratified partition of 16,701 photographs spanning 120 genera and 1,350 species, assessing accuracy, calibration, error structure, species retrieval, and open-set detection of novel genera. DINOv2 attained the best genus performance (macro top-1 66.9%, 95% CI 63.7-70.6; global top-1 88.9%); both ViTs outranked both CNNs, and general-purpose self-supervised pretraining (DINOv2) outperformed domain-matched biological pretraining (BioCLIP 2) by 7.1 points of macro top-1. Errors concentrated on two abundant genera acting as error attractors. DINOv2 embeddings achieved species Recall@5 of 86.6% and genus Recall@5 of 98.7%; temperature scaling reduced every backbone's Expected Calibration Error to about 0.03; and a distance-based open-set gate flagged unseen genera (mean AUROC 0.958). A self-supervised Vision-Transformer backbone combined with embedding retrieval is an effective, deployable strategy for fine-grained identification in species-rich, data-poor floras. The system is released as an open web application (the New Guinea Orchid Identifier), offering a practical template for other hyperdiverse, under-documented taxa.
Read the full abstract

All authors Reza Saputra, Diah Harnoni Apriyanti, André Schuiteman, Kurt Metzger, Ashley Field, Katharina Nargar, William Edwards

Quantitative Methods

Retracing the Process of Translation: Proteome-wide mapping of stable transcriptomic predictors of protein abundance in cancer cell lines

Johannes Schlüter and Alexander Schönhuth

Understanding the relationship between gene expression and protein abundance is central to molecular and systems biology. While gene expression reflects transcriptional activity, proteins are the functional molecules that determine cellular phenotypes. However, numerous post-transcriptional and translational regulatory layers complicate this relationship, and prior studies have reported only weak to moderate correlations between RNA and protein levels. Predicting protein abundance from transcriptomic data remains challenging, but it is a valuable goal for biological insight, especially when proteomic data is limited or unavailable. In this study, we applied a large-scale, Ridge regression-based feature selection strategy to identify predictive gene expression features for each of 8,423 proteins across 940 cancer cell lines. To our knowledge, this is the first work to perform such comprehensive protein-wise feature selection at this scale. Our analysis revealed both globally predictive and context-specific gene features. These included biologically meaningful modules such as immune-related genes, HOX transcription factor targets, and cytoskeletal components. The models identified stable candidate gene-protein associations that remained interpretable at the level of individual proteins and recurrent transcriptomic predictor patterns. Our approach enables interpretable modeling of protein expression from transcriptomic data and provides insight into transcriptomic features associated with protein abundance. This framework may support hypothesis generation, protein imputation in incomplete datasets, and deeper understanding of post-transcriptional regulation in cancer biology.
Read the full abstract

Sunday 20 September

Quantitative Methods

WILSON - a pathology foundation model framework for patient-level analysis and diagnostic text generation

Saghir Alfasly, Wataru Uegami, Sobhan Hemati et al. (+13 more)

Pathologists integrate morphology across magnifications and across the slides of a patient case, whereas pathology foundation models encode thousands of tiles from single slides and aggregate their features. Here we present WILSON, a vision–language foundation model that represents whole-slide images and multi-slide cases as single multi-magnification composite images, trained on approximately 189k slides from Mayo Clinic spanning 42 organs and 829 diagnostic entities using pathology reports as supervision. Without task-specific training, WILSON exceeded a dedicated case-level model on all internal cohorts (macro-F1 0.52 versus 0.38) and matched slide-level models up to 9.4 times larger at 272- to 2,155-fold lower compute. End-to-end fine-tuning on 508 triple-negative breast cancer cases improved histologic subtyping and stromal tumor-infiltrating lymphocyte grading by 0.16 and 0.11 macro-F1. WILSON retrieved matching diagnostic text at 75.6% recall@1 (PRISM, 58.1%) and generated captions closer to report-derived references than PRISM and PRISM2 on the internal cohort and on most external comparisons. Composite images thus offer a compact, clinically aligned computational unit for pathology.
Read the full abstract

All authors Saghir Alfasly, Wataru Uegami, Sobhan Hemati, Wenchao Han, Xiaojia Tang, Kevin Thompson, Daniel Stone, Ghazal Alabtah, Saba Yasir, Michael R. Lucas, Eric W. Klee, Cheryl L. Willman, Judy C. Boughey, Matthew P. Goetz, Krishna R. Kalari, H.R. Tizhoosh

Quantitative Methods · Cross-listed from cond-mat.other

THz Spectroscopy of Urine Vapors from Patients with Prostate Cancer and Benign Prostatic Hyperplasia: A Critical Review and Statistical Reanalysis

V. A. Atduev, A. V. Maslennikova, V. L. Vaks et al. (+7 more)

The cancer specificity of serum prostate-specific antigen (PSA) motivates complementary, non-invasive approaches to prostate disease assessment. Building on reported high-resolution terahertz (THz) analysis of urine-derived products, this review integrates spectroscopic evidence with a statistical reanalysis of clinical data from 24 patients with prostate cancer (PC) and 14 with histologically confirmed benign prostatic hyperplasia (BPH). Nonparametric statistical comparison shows higher PSA levels in PC, while overlapping patient distributions and receiver-operating-characteristic analysis with bootstrap uncertainty estimation demonstrate incomplete discrimination from BPH. Fast frequency-sweep spectroscopy characterizes urine-derived volatile and thermal-decomposition products, distinguishing compounds shared between groups from candidate PC-associated assignments, including glycolaldehyde, butyronitrile, pentanenitrile and methyl isocyanate. Glycolaldehyde has been detected by urinary carbonyl profiling, while benzaldehyde and phenol have been reported in urinary volatile studies. Related aldehydes identified by gas chromatography-mass spectrometry and glycine-associated metabolites reported in proton nuclear magnetic resonance studies provide complementary chemical and metabolic context. These correspondences support plausibility of THz findings without establishing PC specificity. Together, the dataset, statistical assessment and comparative literature synthesis support THz urine spectroscopy as a platform for molecular discovery and candidate prioritization. Standardized sample preparation, separation of native urinary constituents from processing-derived products, and validation in independent cohorts remain necessary.
Read the full abstract

All authors V. A. Atduev, A. V. Maslennikova, V. L. Vaks, A. P. Bavrina, E. G. Domracheva, M. B. Chernyaeva, V. A. Anfertev, K. A. Atduev, Y. Tawalbeh, M. F. Pereira

Saturday 19 September

Quantitative Methods · Cross-listed from cs.CV

Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology

Swarn Warshaneyan, Joial Danyal, Blaž Cugmas et al. (+4 more)

Automated pollen analysis supports veterinary cytology, but brightfield microscopy is costlier and more complex than lens-less digital in-line holographic microscopy. We evaluate whether reconstructed holograms can narrow this gap and whether model explanations remain reliable under modality change. Six pollen species were imaged by brightfield and holographic microscopy. Raw, single back-propagation and iterative phase retrieval holograms were evaluated with YOLOv26s detection and MobileNetV4 classification after anchor-based annotation transfer. Six attribution methods were assessed for spatial grounding and faithfulness with the Attribution Health Inspection and Repair (AHIR) protocol, which tests model brittleness under weak noise and corrects attribution-map granularity when needed. Brightfield achieved 0.6890 mAP50-95 (0.8865 mAP50) for detection and 0.9687 macro-F1 (0.9705 accuracy) for classification. Reconstructed holograms narrowed the gap with a task-dependent split: p-type was strongest for detection at 0.5324 mAP50-95 (0.8229 mAP50), while r-type was strongest for classification at 0.7695 macro-F1 (0.7866 accuracy), both far above raw-hologram baselines. Activation-based explanations localized strongly on grains, and region-based methods retained ~60 to ~80% of faithfulness under holography. The holographic detector was highly brittle to weak perturbations, saturating deletion-based evaluation while insertion remained informative. Pixel-level gradient explanations approached random floor, yet spatial smoothing restored p-type gradient faithfulness from 0.05 to 0.51. For holographic classification, perturbation-based explanations remained faithful while gradient-based methods fell below random floor. Reconstruction improves low-cost holographic pollen analysis, while AHIR distinguishes genuine attribution failure from artifacts caused by model brittleness and map granularity.
Read the full abstract

All authors Swarn Warshaneyan, Joial Danyal, Blaž Cugmas, Mindaugas Tamošiūnas, Edgars Kviesis-Kipge, Kirishanth Manivannan, Roberts Kadiķis

Quantitative Methods · Cross-listed from eess.SY

Experimental Design for Controller Selection in Synthetic Biology

Eric Palanques-Tost, Ron Weiss and Calin Belta

Synthetic biology enables the design of genetic circuits that act as feedback controllers. These controllers are typically designed using computational models, but mismatch between model and real dynamics can lead to controllers that fail in practice. While methods to address this issue exist, synthetic biology introduces additional structural constraints. Genetic circuits are often highly constrained by experimental limitations, reducing controller design to selection among a limited set of implementable circuits rather than an optimization over a continuous space. As a result, multiple system hypotheses may lead to the same optimal controller within the implementable set. Reducing model uncertainty may therefore be irrelevant when the models lead to the same optimal controller. In this paper, we exploit this structure to develop an algorithm for controller selection in synthetic biology, formulating the problem as a decision-oriented experimental design problem over a finite controller set. We represent plant uncertainty using a set of hypotheses and select experiments to minimize the posterior controller selection risk, rather than global model uncertainty. Across three mechanistic case studies, our method reaches the stopping criterion in fewer experimental rounds than model uncertainty and random experiment selection policies, while maintaining a comparable success rate.
Read the full abstract

Friday 18 September

Quantitative Methods

Improving scoring functions for protein-protein docking with LambdaLoss

Richard Zhu, Darren Xu, Lee-Shin Chu et al. (+1 more)

Modeling protein-protein interactions requires accurate scoring functions that can rank potential poses (conformations) of a protein-protein complex to differentiate near-native poses from incorrect ones. Here, we propose a general framework for improving protein-protein pose ranking and other biomolecular interaction models using the LambdaLoss loss function from the Learning-to-Rank field. We test this framework by fine-tuning the energy prediction head of DFMDock with the LambdaLoss on an augmented dataset of 2.9M decoy poses derived from the DIPS dataset. On targets from the CAPRI score set benchmark, our fine-tuned ranking model LambdaDockScore is better at identifying correct poses in its top-1 and top-5 predictions compared to EuDockScore, a state-of-the-art method. LambdaDockScore also improves upon baseline DFMDock ranking performance for scoring antibody-antigen complexes and protein-protein complexes with very large or small binding interfaces.
Read the full abstract

All authors Richard Zhu, Darren Xu, Lee-Shin Chu, Jeffrey J. Gray

Quantitative Methods · Cross-listed from cs.LG

EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents

Xinye Yang, Yuli Wang, Cheng Ting Lin et al. (+1 more)

Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires reliable histories of patient conditions, treatments, and the information available at each decision. Electronic health records (EHRs) contain these histories, but differences in how events are recorded make them difficult to use consistently. We present EHR2Trace, a system that converts EHRs from different sources into traceable patient events for model training and evaluation. It links events to source records, separates event time from information availability, and distinguishes medication orders, dispensing, and administration. A shared event representation supports both OMOP and MEDS exports, with automated validation and reproducible builds. Across three clinical datasets, EHR2Trace converted 846.4 million events, with every applicable check passing except one unit-consistency check on MIMIC-IV, and detected all 28 injected faults. A controlled prediction experiment showed that assigning later diagnoses to admission time substantially inflated measured performance, and that a model trained on such data lost accuracy when deployed on histories filtered by availability. EHR2Trace provides a reusable data foundation for patient world models and clinical agents, helping researchers inspect patient histories, check conversion decisions, and evaluate models with explicit data rules.
Read the full abstract

All authors Xinye Yang, Yuli Wang, Cheng Ting Lin, Harrison Bai

Quantitative Methods

Reactive molecular dynamics simulations of atenolol first steps degradation by 9CL6 ammonia monooxygenase

Pascal Brault, Matthieu Wolf, Yana Gouzi et al. (+2 more)

The persistence of beta-blockers like atenolol in aquatic environments necessitates efficient remediation strategies, such as enzymatic biodegradation. This study employs reactive molecular dynamics (rMD) simulations to investigate the initial degradation steps of atenolol by the oxidoreductase 9CL6 ammonia monooxygenase. Using the ReaxFF reactive forcefield within a simulated aqueous environment, the degradation processes were modeled at 300 K and 350 K over 6.5 nanoseconds. Results indicate initial degradation rates of 24% at 300 K and 18% at 350 K, with each enzyme molecule degrading approximately 20 atenolol molecules before reaching a saturation point. Mass spectrum analysis reveals the primary formation of C8 and C6 fragments at both temperatures. However, at 300 K, additional intermediate fragments (C1, C3, C11, C13) are observed, which are completely bypassed at the higher temperature of 350 K. Furthermore, increasing the temperature to 350 K accelerates the initial degradation phase from 2 ns to 0.5 ns, despite yielding a slightly lower overall degradation rate. Ultimately, these atomistic insights provide a foundational computational methodology for predicting biodegradation rates and pathways of pharmaceutical contaminants at the molecular scale.
Read the full abstract

All authors Pascal Brault, Matthieu Wolf, Yana Gouzi, Claire Albasi, Jeanne Trognon

Quantitative Methods

High Reconstruction Quality and Restart Repeatability Do Not Guarantee Recovery of Ground-Truth Muscle Synergies

Ye Ma, Dongwei Liu, Meijin Hou et al. (+1 more)

High reconstruction quality and agreement across repeated fits do not necessarily establish recovery of muscle synergies. We tested whether a variance-accounted-for (VAF)/elbow rule recovers the generating synergy count and spatial vectors, whether high restart repeatability indicates recovery, and how five design factors affect recovery. Non-negative matrix factorisation was applied to 4,320 synthetic 16-muscle datasets varying generating rank, noise, trial count, spatial similarity and activation overlap. Combined recovery required the correct rank and cosine similarity of at least 0.80 for every matched spatial vector. Factor effects and two-factor interactions were assessed using exploratory heteroscedastic Wald tests with Benjamini-Hochberg adjustment. Rank selection was exact in 17.6% of datasets, too low in 54.9% and too high in 27.5%; combined recovery was 13.9%. Among fits with VAF at least 0.90, only 11.3% achieved combined recovery. Among 3,762 datasets with spatial repeatability at least 0.95, 19.6% had the correct rank and 15.7% achieved combined recovery. All five factors were associated with recovery (adjusted p < 0.001). Recovery declined from 26.2% to 1.7% with increasing spatial similarity and from 26.2% to 2.2% with increasing activation overlap. It was lower at ranks 7-9 than at 3-5, increased from 11.0% with 3 trials to 15.8% with 80 trials, and varied non-monotonically with noise. Five noiseless signals synthesised from measured-sEMG reference factors also showed under-selection despite VAF above 0.918. Under this selector, high reconstruction quality and restart agreement were insufficient indicators of correct rank and spatial recovery. Muscle-synergy interpretation should account for rank sensitivity and the separability of spatial and activation patterns.
Read the full abstract

All authors Ye Ma, Dongwei Liu, Meijin Hou, Chenyi Guo

Quantitative Methods · Cross-listed from q-bio.NC

Identifying Neural State Changes due to Gain versus Off-Manifold Displacement

Sam McKenzie

Memory segmentation is thought to arise from rapid decorrelation in neural activity, often quantified by Euclidean distance or cosine angle. Although these metrics detect a transition, they do not reveal how the new state relates to the repertoire represented by the neural manifold. This matters because neuromodulators that drive state transitions also alter excitability, and learning may repurpose existing representations or create new ones. Here, I introduce a geometric decomposition that separates changes attributable to gain modulation of a nearby manifold state from movement within the manifold and genuine off-manifold displacement. The approach uses the radial axis of neural population activity to partition the normal space of a local manifold region. A central challenge is identifiability: given only a static reference manifold and a single test state, neither the state from which a perturbation began nor its gain magnitude and mechanistic decomposition can generally be recovered uniquely. I therefore formulate identifiability as a cascade of geometric gates specifying when each component can be interpreted. The gates distinguish structural failures, including the absence of a local chart or incorrect intrinsic dimensionality, from estimation error and systematic bias caused by reference sampling, tangent-frame error, gain-axis misalignment, anchor displacement, and poor ratio conditioning. Simulations show that neighborhood size, curvature, sampling density, ambient dimension, and noise act through a small set of geometric quantities. The framework specifies when assignments to gain or novelty are identifiable, how they become biased, and which diagnostics reveal the relevant failure regime. By quantifying the nature rather than only the magnitude of neural state change, it provides a clear, readily interpretable framework for evaluating mechanisms of neural state transitions.
Read the full abstract

Quantitative Methods · Cross-listed from cs.LG

Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization

Lingfei Kong

Sparse longitudinal CT follow-up limits lesion-size forecasting when only a few prior observations are available. We constructed a five-visit DLT-derived same-lesion trajectory benchmark from DeepLesion and Deep Lesion Tracker (DLT), yielding 205 trajectories from 129 patients. We compared an exploratory conventional sparse-to-final analysis with a primary fixed visit-index horizon design predicting the common log change from T3 to T4 while progressively adding earlier observations, evaluating predictive accuracy, uncertainty reliability, post-hoc conformal interval calibration, subgroup performance, and Gompertz-inspired trajectory regularization. The evaluated methods showed partially overlapping point-prediction accuracy but distinct uncertainty behavior. Mean held-out RMSE across ten training seeds was 0.4726, 0.4305, 0.4499, and 0.4513 for m = 1, 2, 3, 4, indicating the lowest mean RMSE at m = 2; additional history did not improve RMSE. At m = 4, raw Cohort-Level Feature GP coverage was near the 95% nominal level, whereas MC Dropout, Deep Ensemble, and residual-scale intervals were conservative. Patient-level conformal calibration generally produced near-nominal or conservative coverage at the cost of wider intervals. Patient-grouped development cross-validation selected lambda* = 0 for the Gompertz-inspired term. A global population reference frequently opposed lesion-level change directions, and prediction difficulty varied across anatomical subgroups. Overall, additional historical observations provided limited predictive benefit once the prediction horizon was controlled, while predictive accuracy, uncertainty reliability, and trajectory consistency did not necessarily improve together, and should be evaluated jointly in sparse longitudinal imaging.
Read the full abstract

Thursday 17 September

Quantitative Methods

Foundation-model-based multi-label phenotyping of combined hyperkinetic movement disorders

Laura Cif, Zohra Souei, Diane Demailly et al. (+13 more)

Movement disorders (MDs) frequently co-occur, yet phenomenological and severity assessment shows substantial inter-rater variability. Markerless video could improve reproducibility, but prior work is largely single-symptom, depends on standardized acquisition, and lacks validation and transfer across ages and sites. We combined two foundation models into one frozen backbone: Segment Anything Model 3 (SAM 3) for dense, per-frame markerless segmentation summarized into geometric, contour and grid kinematic signals, and TabICLv2, a tabular foundation model, for in-context multi-label classification of eight hyperkinetic MD phenomenologies. Trained on standardized recordings of 21 adults and 4 controls, it transferred unchanged to two independent datasets, pediatric (n=12) and tremor-dominant adult (n=20), assessed with the CODY-SAMP scale; only the patient-level decision step was recalibrated per site. Under clinician consensus labels, false positives fell to zero in both datasets. Dystonia recovered perfectly (7/7 pediatric; 15/15 adult held-out), chorea fully in children (3/3), and tremor was recovered in adults (11/15) once a tremor-rich cohort made it evaluable, through recalibration alone. Per-region effect-size analysis gave clinically coherent, phenomenology-specific signals and identified myoclonus as the principal failure. Against YOLOv8 sparse keypoints, the dense representation matched under clinician permissive labels (Jaccard 0.63 vs 0.63) and was markedly more robust under clinician-label consensus (0.93 vs 0.76). This frozen foundation-model backbone with light per-site calibration yields transferable, interpretable, conservative multi-label phenotyping of co-occurring hyperkinetic MDs across ages and from standardized to routine video, adding robustness on high-confidence, clinician-agreed labels. Prospective multi-centre validation is required before clinical use.
Read the full abstract

All authors Laura Cif, Zohra Souei, Diane Demailly, Mayte Castro-Jimenez, Juan Dario Ortigoza-Escobar, Muhammad Mushhood Ur Rehman, Morgan Dornadic, Sophie Huby, Gun-Marie Hariz, Cecile Hubsch, Nathalie Dorison, Eduardo M. Moraud, Jocelyne Bloch, Gabriella Horvath, Olivier Oullier, Xavier Vasques

Quantitative Methods · Cross-listed from physics.med-ph

Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy

Sebastián A. Cruz Romero

Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on laboratory CPUs and edge hardware requires compression schemes that are both efficient and auditable. We present a deployment-oriented evaluation of compressed Cellpose-SAM using a pre-specified retention criterion: the 95% cluster-bootstrap interval of mean change from FP32 must remain above a fixed -0.02 margin for every imaging modality. On a stratified 176-field panel spanning BBBC038 nuclei, BBBC039 U2OS fluorescence, and NIST iPSC images across density regimes, weight-only W8A16 preserves instance F1 across all modalities. A sensitivity-guided mixed W4/W8 scheme, using four INT8 exceptions, achieves a 6.76x reduction in weight storage with no observed catastrophic failures (0/176 fields), matching W8A16 at this sample size. In contrast, ternary weight-only quantization achieves 12.08x compression but fails catastrophically on 169/176 fields. These results demonstrate that compression should be evaluated by modality-stratified downstream retention rather than single-number accuracy, and establish a reproducible protocol for auditing compressed foundation models in regulated stem-cell imaging.
Read the full abstract

Quantitative Methods · Cross-listed from cs.LG

Dynamic Generalized Gromov-Wasserstein Optimal Transport

Junda Ying, Zhiwei Zeng, Peijie Zhou et al. (+1 more)

Gromov–Wasserstein optimal transport (GW-OT) extends classical optimal transport by introducing structure-aware transport cost. This is particularly relevant for spatial transcriptomics, where dynamical reconstruction should preserve tissue structure in addition to matching expression patterns. While static formulations have been widely used for such structure-aware alignment, a general dynamic formulation for reconstructing continuous trajectories is still missing. We introduce Travelling Pair Dynamical Alignment and Trajectory Estimation (TP-DATE), a theoretical and computational framework to generalize GW-OT dynamically in a simulation-free manner. We formulate a broad class of static and dynamic Quadratic-form OT (QOT) through path actions and prove the static dynamic equivalence. We further develop travelling-pair flow matching, which allows interacting conditional paths and marginalizes their interactions into a single vector field. On synthetic and real spatial transcriptomics data, TP-DATE better preserves spatial structure and improves continuous 3D dynamics reconstruction.
Read the full abstract

All authors Junda Ying, Zhiwei Zeng, Peijie Zhou, Lei Zhang

Quantitative Methods · Cross-listed from physics.med-ph

T2 estimation from MOLLI acquisitions

Catarina N Carvalho, Andreia S Gaspar, Rita G Nunes et al. (+1 more)

Cardiac T1 and T2 quantitative magnetic resonance imaging (MRI) is a technique that provides characterization of a multitude of myocardial pathologies. However, each parameter requires its own specialized acquisition sequence, which may be time-consuming. In this work, we demonstrate that MOLLI, an acquisition sequence commonly used to perform T1 mapping, is also sensitive to T2, and can also be used for myocardial T2 mapping. Although MOLLI is not designed for T2 mapping, its signal evolution inherently depends on both T1 and T2 relaxation. Here, we demonstrate that this dependence is sufficiently strong to allow T2 estimation directly from MOLLI T1-weighted images, using appropriate signal modelling. This finding opens the possibility of obtaining simultaneously T1 and T2 maps from a single MOLLI acquisition, reducing total scan time and potentially improving patient comfort and clinical throughput.
Read the full abstract

All authors Catarina N Carvalho, Andreia S Gaspar, Rita G Nunes, Teresa M Correia